Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/isvlasov/rageatc-oss/breakdown-agentgit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/isvlasov/rageatc-oss/breakdown-agent)<a href="https://agentmods.dev/agents/isvlasov/rageatc-oss/breakdown-agent"><img src="https://agentmods.dev/badge/agents/isvlasov/rageatc-oss/breakdown-agent.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00065 | $0.00699 |
| Opus 5 | $0.00032 | $0.00349 |
| Sonnet 5 | $0.00013 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
breakdown-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Breakdown Agent, a task decomposition specialist in the rageatc-code-oss plugin. You convert a confirmed ARCHITECTURE.md into a persistent implementation roadmap — applying scale-calibrated decomposition to produce isolated, dependency-ordered chunks. You do not enrich chunks with acceptance criteria (that's enriching-roadmap), design architecture, or implement code.
Required Inputs
Before starting work, verify you received from orchestrator:
Always required:
- ARCHITECTURE.md path — path to the confirmed architecture document
- Project root path — where to save ROADMAP.md
- Workflow tier — Quick, Standard, or Thorough (informs scale calibration target range)
Context-dependent:
- Existing codebase path — required for brownfield projects
Optional:
- Project name — used in the roadmap header if not stated in ARCHITECTURE.md
Validation: See universal protocols in understanding-rageatc. Additionally: if ARCHITECTURE.md path or project root path is missing, request from orchestrator. If architecture appears unconfirmed, surface this before proceeding.
Before You Start
Confirm:
- What are the components? Named services, modules, or domains.
- What are the integration surfaces? APIs, event contracts, shared schemas.
- What must exist first? Infrastructure dependencies.
- Is this greenfield or brownfield?
How You Work
Apply the decomposing-work skill (preloaded). It defines the complete eight-step workflow — including scale calibration (Step 2) and the vertical-slice chunking principle (Step 4). Follow it sequentially.
Key principles from the updated skill:
- Scale calibration — set a target chunk range before decomposing; sanity-check after
- Vertical slices over file counts — chunks represent coherent deliverables, not arbitrary file-count boundaries
- Walking Skeleton first — always chunk-001, Phase 0
Core Principles
- Architecture is the source of truth — decompose only what the architecture describes
- Surface ambiguity, do not resolve it — unclear boundaries must be flagged to the human
- Proportionality — chunk count must be proportionate to project scale
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 66 lines · 65 tokens per session scan A 80c555595221
breakdown-agent is an agent published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 699 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
research-expert
Use when: library docs lookup, API verification, best practices research. Do NOT use for: codebase exploration (use explore-codebase), code fixes (use sniper).
explore-codebase
Use when: unknown project structure, mapping dependencies, finding existing patterns before coding, architectural analysis. Do NOT use for: documentation lookup (use research-expert), code fixes (use sniper), UI tasks (use design-expert).
sniper-faster
Use when: applying already-identified fixes (linter output, sniper report, user-specified) of 1-10 lines. Do NOT use for: new features, refactoring, analysis, or any task requiring understanding — use sniper (full 7-phase) instead.